Custom agents

AI 网文长篇小说写作流水线，12 个 skill 包。配套站点 novelcatch.com：番茄每日扫榜 / 拆书 / 情报（免费）

AI-agent skill for creating, auditing, and maintaining Penpot design systems, prototypes, tokens, and design-to-code workflows via the official Penpot MCP Server.

Open source coding agent workspace, an agent-first desktop app that runs locally. alternative to Cursor and Codex.

A comprehensive guide and resource collection for building sophisticated agentic AI systems with LangGraph.

A local-first desktop application for AI agent workflows.

Loop Engineering — a skill for designing & reviewing autonomous/semi-autonomous agent loops (Claude Code, Codex, Copilot, Gemini).

Chinese adult-oriented AI text GalGame agent skill with freeform roleplay, story memory, and novel export.

Multi-agent demo for Statewave conflict resolution. Concurrent agents write to a shared subject; the compiler detects contradicting facts via Jaccard similarity and supersedes the stale one with provenance. FastAPI + SSE, Apache-2.0.

Search knowledge by what documents mean and how they look — not one or the other.

Unofficial LINE API Python SDK — automate your personal LINE Messenger account: QR code login in your terminal, send/receive messages, E2EE Letter Sealing, bot framework & CLI. No developer account, no webhook. Reproduces the LINE Chrome extension protocol (CHROMEOS 3.7.2, X-Hmac/WASM). pip install okline.

Agent-ready MATLAB and Simulink skill suite for Codex: batch execution, validation, codegen, simulation, and reproducible research workflows.

开源免费的 Windows 桌面日历：待办清单、日程提醒、农历节假日、四象限、倒计时和 AI 周报

Protected remote debugging bridge for an existing iOS WKWebView

OpenFang 中文本地化版：面向中文用户的开源 AI Agent OS

Context Diet is a Claude Code agent skill for measuring system-prompt overhead, reviewing tool payload size, and reducing unused definitions through controlled settings.json configuration.

ash4d.com is a self-hosted private AI platform for k3s Kubernetes, combining local Qwen3 inference, retrieval-augmented generation, agent tooling, and GPU-enabled services in a GitOps-managed environment.

Prepare any codebase for AI. Wires OpenCode, OpenSpec, codegraph, and agentmemory into a multi-agent development workflow powered by native parallel subagents.

Agent-SDK without CLI dependencies, as an alternative to claude-agent-sdk, completely open source

Deterministic safety floor for tool-using AI agents: pre-execution gating, SafeFix suggestions, attack-chain detection, opt-in self-learning LLM judge. Papers: arXiv 2605.04785, 2606.08539

Framework for building sophisticated Investment Research AI agents .

[EMNLP 2026 Main] Think, Act, Build: An Agentic Framework with Vision Language Models for Zero-Shot 3D Visual Grounding

An OWASP-aligned intentionally vulnerable platform for learning and testing AI, LLM, RAG, MCP, and Agentic AI security.

AI 视频脚本创作助手 通过自然语言对话生成专业 Seedance 2.0 视频脚本和分镜提示词的 Web 应用。基于 Claude Agent SDK 构建，内置完整的视频脚本创作技能，支持从故事分析到分镜脚本的全流程 AI 创作。

Self-healing, config-as-code stack for the OpenCode AI coding agent — one key, 17 curated OpenRouter frontier models (GLM/DeepSeek/Gemini/Qwen/Kimi), multi-agent teams, cost guards, telemetry off. Claude Code / Cursor alternative on your terminal.

Sage is a skills framework that makes AI agents think before they act, stay focused under complexity, and deliver outcomes you can trust. Built for product and engineering teams, open to any domain.

The open-source workspace for coding agents. supermux runs Claude Code, Codex, and other coding agents on your own computer or server, many sessions at once, and lets you work with them from your desktop or phone.

AI-native financial intelligence platform for accounting, financial reporting, and investment management. Models your ledger, reports, and portfolios as a knowledge graph that AI agents can query and operate. Fork-ready: GitHub Actions CI/CD deploys the CloudFormation infrastructure to your own AWS account.

Turn reference images into Minecraft-native Blockbench models using agent reasoning and deterministic compilation.

Local AI Skills central library with per-project symlink enablement. One AISkills folder holds every skill source; symlink on demand into any project's .agents/skills or .claude/skills to share across Claude Code, Codex, OpenCode, and Pi.

Your Hermes agents, one shared brain.

Vendor-neutral Go CLI for the Open Knowledge Format. Create, validate, lint, index, search, and graph OKF bundles. Built to be driven by AI agents.

An open-source browser extension—a gateway with two-sided reach into search, with locally managed credentials—for humans and local AI agents.

Open-source security for AI coding agents: record, detect and block at the tool boundary, with a verifiable audit trail in the SIEM you already run.

Checks every AI agent action against your company's real rules before it runs. Git-native, PR-reviewed.

Ask your data a question — get charts, insights and a public dashboard link. 46 analytical tools, ML forecasts, prod-DB connections. Runs on budget LLMs like Deepseek V4 Flash.

Read-only Kubernetes troubleshooting agent in Go (client-go) — explains CrashLoopBackOff, ImagePullBackOff, OOMKilled, Pending/Unschedulable with P1-infra to P2-workload reports; guarded reversible --fix; optional AI --explain via Claude API.

An open-source DSL and compiler for floor plans: write .arch source (or have an AI agent write it) and compile it to SVG, DXF or PDF with linting and geometric validation.

AI marketing agents for Claude Code: a B2B SaaS marketing team as a plugin. 91 agents in 17 disciplines, CATALYST orchestrator, 19 skills and a Campaign Board mod. SEO/AEO/GEO, content, paid, social, email, ABM, PLG, PMM, pricing, sales/presales, partners, analytics. Missing facts come back as [NEEDS INPUT], never invented. Also works in Cursor.

Your AI works the night shift — read-only reviews of your projects while you're busy, one digest every morning.

小丑鱼（Clownfish）：本机优先、带长期记忆的 AI 工作应用，支持对话、能力任务、办公文件与持续工作。

Autonomous offensive-security agent: recon, authorized pentest, vuln hunting, DFIR & multi-framework compliance from a single prompt. Local-first (llama.cpp), skill-based, deterministic-first.

Claude Code skill for planning, executing, and measuring digital marketing campaigns. Includes UTM tracking, content strategy, email sequences, social media tactics, brand voice guidelines, and analytics frameworks.

Turn research and long-form writing into humanistic, model-interpreted Xiaohongshu carousels.

Based on Hermes Agent's `llm-wiki` skill and Andrej Karpathy's LLM Wiki pattern; extended with multimodal ingestion and provenance hardening.

企业级多智能体AI管理系统 | 企业级智慧管理解决方案 | 基于MCP架构的财务分析、成本预测、知识管理、效能评估一体化平台|- 多智能体系统 (Multi-agent System) - MCP协议 (Model Context Protocol) - - AI决策支持系统 - 企业级AI应用 - Python + FastAPI + Streamlit

免登陆一键保存小红书笔记到本地的 Skill，适用于 Claude Code/Codex/OpenClaw 等 agent

kixparadigm — AI self-orchestrated minimal paradigm (resident cognition layer) + kixpower multi-agent orchestration · one-command import into DeepSeek Harness (npm i -g) / AI 自编排最小范式（认知层常驻）× kixpower 多智能体编排 · npm 一键导入 DeepSeek Harness

Generate project-tailored AI assistant rules & skills (CLAUDE.md, .cursorrules, Copilot instructions, AGENTS.md) in under two minutes. Works with Claude, Cursor, Copilot, Codex, Windsurf, Antigravity.

🎬 Autonomous AI agent that transforms long-form videos into viral short-form content across YouTube Shorts, TikTok, and Instagram Reels using advanced AI analysis and automation.

You're the boss. Claude and Copilot are your employees. Give them desks, assign them work, and watch them build — in a pixel-art office.

Red-team your RAG pipeline for prompt injection, source-document leakage, and cross-document smuggling, in CI. The gap between RAG eval (RAGAS/DeepEval) and LLM scanners (garak).

Moved to PostHog/coherence — development continues there as @posthog/coherence.

A local-first context engine designed for seamless human-agent and multi-agent collaboration. It systematically synthesizes, organizes, and maintains multi-format workspaces, turning raw notes, code, tables, and documents into a structured, high-signal knowledge base accessible to both users and autonomous agent ecosystems.

Design Skills for Agents

A comprehensive skill library for Element Plus UI framework, designed for AI agents to understand and utilize Element Plus components effectively.一个全面的 Element Plus UI 框架技能库，专为 AI 智能体理解和运用 Element Plus 组件而设计。

Resonant Open System Toolkit (Multi-Agent AI) - Runs on OpenClaw + your custom AI

Drive the Chrome you are already logged into - from your terminal or any AI assistant. Cross-platform, MCP-ready.

Grux AI: open source AI agent for macOS (MIT). One Command Panel for your mail, calendar, meetings, files and a shell it can undo. Runs on a local Ollama model with no key, or your own key. Change it with Claude Code. Download Grux.dmg at gruxai.com, or brew install --cask dotcomjack/tap/grux

Log workouts, runs, meals, and body weight through WhatsApp using Cloudflare Workers, D1, and GPT-5.6 Luna

AI Desktop Pet brings animated companions to your desktop with window-aware movement, screen vision, memory, and real-time conversations powered by Convai.

Production-ready Git workflow skills, agents, hooks, reviews, releases, and notifications for Claude Code and Codex.

Persistent memory MCP server for AI agents — Rust, 19 tools, knowledge graph, Hebbian learning, episodic memory, contradiction detection, prospective triggers, Bayesian calibration, zero-config Docker setup.

AI-ready knowledge base of security & compliance regulations for hardware and connected-device manufacturers - structured, indexed, and machine-readable for LLMs and agents.

Repo-native AI orchestration engine — connects issue trackers (GitHub, GitLab, Linear, webhooks) to coding agents (Claude, Codex, Copilot, Pi) with isolated workspaces and a live TUI.

AI agent governance for teams. Runtime firewalls tell you what happened; Conduct Guard controls what can happen — signed policy, verified chain, fail-closed by default. Ships with Router (LLM proxy), 20+ compliance packs, canvas UI, and a playbook engine.

TypeScript knowledge graph RAG for AI agents: source evidence, hybrid retrieval, MCP integration, and a permission-aware PostgreSQL runtime.

Self-hosted AI companion with a simulated daily life, long-term memory, and consistent-identity selfies. Your keys, your data, your machine.

Personal collection of agent skills using the open SKILL.md standard. Works with Claude (claude.ai, Claude Code, API), Cursor, and other AI assistants.

AI-native, source-available (PolyForm Perimeter) game-dev toolkit: bforge — deterministic headless-Blender asset forge for AI agents (138 ops, quality-gated) — proof-carrying asset/entity/world compilers, deterministic Python/Rust/Wasm simulation, glTF into Babylon.js/three.js/Godot, Rust services. Godot 4.7.1 Forward+ on WebGPU, reproducibly.

RPG Maker MV Copilot MCP — Debug events, edit maps, and playtest RPG Maker MV projects with AI.

Portable, evolving context and workflow layer that works across Claude Code, Codex, Hermes Agent, OpenClaw, Cursor, Devin and other compatible coding agents. All backed by Git.

A curated survey of embodied agents:robotic memory, planning, world models, verification, and failure recovery

OWASP GenAI Data Security Initiative — taxonomies, crosswalks, datasets, and tooling for securing data in generative AI systems

Self-hosted RAG knowledge base for docs and code, searchable by Claude Code and other agents over MCP

基于SpringAI ReAct智能Agent的摄影预约系统，与行业结合，自研多轮推理调度，集成RAG向量知识库，支持自然语言业务工具调用。

AI 原生的数据大屏 / BI 可视化编辑器：用自然语言或截图描述需求，多 Agent 协作搭大屏、接数据、配联动，AI 生成配图和视频素材，改动实时同步到画布。

🛠️ Chatbot generator for Intelligo Framework.

A Claude skill that guides you through building your own AI command center for your business — own your systems, connect your tools, expose them over MCP, unify under one command layer.

Build your AI Second Brain with Claude Code — companion starter kit for the ODSC Personal AI Agents Summit 2026

Набор агентских скилов (Agent Skills для Claude Code и Codex), позволяющих владельцу магазина на Яндекс.Кит управлять магазином из AI-агента: каталог, цены и остатки, заказы, промокоды, коллекции, витрина.

目标打造全球跨境卖家的开源 AI 全能运营助手：基于 LangGraph、RAG 与多智能体协作，连接 Amazon、独立站、ERP 和广告平台，覆盖市场洞察、智能选品、竞品监控、关键词研究、Listing 优化、广告投放、销量预测、库存补货、利润核算、客服分析、合规风控、内容营销、知识问答、运营报告和自动化任务。支持多模型、人工审核、私有部署和团队协作，让数据采集、分析、决策与执行形成可追踪、可扩展的运营闭环。持续建设，欢迎共建。

MCP server that connects AI agents ( Claude, ChatGPT, Gemini, Cursor etc.) to OPC UA systems - read, browse, history, subscriptions, events and alarms.

国内电商skill: 国内可以访问api，费用正常不贵，功能齐全（生图生视频生语音），世界最好的AI集合，apiz服务达到可用。本 Skill 封装了 [apiz.ai](https://apiz.ai) API 网关服务的 CLI 工具使用，让 Claude 能够通过 apiz 访问数百种主流 AI 模型，涵盖**图像生成、视频生成、音频处理**等能力。目标是方便 agent 直接理解和使用 apiz，而无需查询接口和参数。

基于Spring AI + LangGraph4j 工作流 + RAG 知识库 + Redis 高并发优化 + Dubbo微服务架构（7个独立服务）/单体架构+ Higress 云原生网关的教育智能体平台

AI-powered desktop app that provides real-time interview assistance. Get instant, professional answers to interview questions with screen-share safe technology.

AI agent skill pack for RPG Maker MV/MZ — teaches Claude Code, Codex, and Cursor to safely read and write RPG Maker project files

Marketing & growth skills for AI agents (Claude Code, OpenClaw, etc.)

Mirror of MengTo/Skills — agent skills for Codex, Claude, and Cursor (MIT, © Meng To). Upstream: github.com/MengTo/Skills

NEW [🔥 updating...]LLM 驱动的股票量化因子挖掘与交易平台，现在支持MCP接入Codex、Claude Code。支持A股:多 Agent + 公式化挖掘、Qlib 回测、Web 门户、日频信号、Telegram/飞书 通知。

🏛️ Agente IA jurídica completo com N8N, GPT-4 e WhatsApp Business - Análise de documentos, transcrição de áudios e geração de contratos automatizada ⚖️

DSH (DeepSeek Harness) web GUI plugin collection — task notifications, provider usage, LAN proxy, MCP manager, worktree sidebar, isolated browser verification. Targets dsh release candidates (rc only, no alpha); exact baseline in README. Install: dsh plugin --profile web add @wingsky-1/dsh-plugins-all

Local-first pentest agent: Go daemon + React dashboard + Codex/Claude Code/Pi runtimes, scoped projects, Blackboard, sandbox runners

The AI frontend you can reshape just by asking.

An open database of real-world AI agent incidents.

Pi coding agent extension for focused code retrieval, grounded edits, safety checks, and language-server support.

Scrub Data: A Framework for Reproducible Data Curation with AI Coding Agents

explicit intent layer for agent-to-agent protocols and token-efficient RAG discovery.

Run coding agents autonomously with isolated Git worktrees, independent verification, and human-controlled integration.